Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances where something is still ongoing or in existence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ongoing existence or state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    catentry
    -0.63
    guyen
    -0.63
    ision
    -0.63
    sonian
    -0.62
    ggles
    -0.62
    imeter
    -0.61
    PsyNetMessage
    -0.60
    osterone
    -0.60
    isson
    -0.60
    ingly
    -0.59
    POSITIVE LOGITS
     alive
    1.52
     here
    1.14
     around
    1.11
     Alive
    1.09
     there
    1.09
     active
    1.09
     awake
    1.07
     present
    1.07
     asleep
    0.98
     lurking
    0.98
    Act Density 0.334%

    No Known Activations